Self-Learning Integrity Management System and Related Methods

Abstract

An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.

Description

RELATED APPLICATION[0001]This application relates to U.S. Utility application Ser. No. 11 / 535,787, filed Sep. 27, 2006, entitled “System and Method for Generating and Using Fingerprints for Integrity Management,” the contents of which are incorporated by reference herein in its entirety.TECHNICAL FIELD[0002]The present disclosure relates to a system for analyzing variations in complex systems that occur over time and, more particularly, to a system and method for providing integrity management through the real-time monitoring of such variations and the alerting of potential effects from such variations before such effects occur.BACKGROUND[0003]Complex systems are all around us. From weather to ecosystems to biological systems to information technology systems, various tools have been developed in attempt to study and understand these systems in detail, mainly through the use of computer-analyzed data. Using computers, information may be analyzed and presented for human consumption a...

AI Technical Summary

Benefits of technology

[0008]An integrity management system and method is provided that monitors variations or abnormalities in complex systems, such as an IT infrastructure or other types of systems, to predict the occurrence of an event before the event occurs based upon similarities to a prior history of variations or abnormalities within the complex system. The integrity management system generates a topology of the nodes of the complex system and collects data from the system based on predetermined metrics. In one aspect, the predetermined metrics are selected from desi

Problems solved by technology

For all of their power in accomplishing these tasks, however, existing tools to date suffer from an inherent inability to predict future events with accuracy in these complex systems.

The problem with prior approaches is that computers are only capable of performing the tasks they are programmed to analyze.

In most cases, the human operators are not able to instruct the computer how to model each variable in a complex system with enough precision to tell the computer how to make the predictions.

For instance, in the case of an information technology (IT) infrastructure, these variations from normal or expected operation could lead to failures, slowdown, threshold violations, and other problems.

Often, these types of problems are triggered by unobserved variations or abnormalities in one or more nodes that cascade into larger problems until they are finally observable.

Other tools are based on inefficient thresholding systems that address the potential abnormality when the probability that the abnormality will lead to an a

Images